EPISODE · Feb 16, 2026 · 55 MIN
=Coffee
from Hacked · host Hacked
A lot of modern AI models have a kind of security guard layer that sits in front of them. Its job? A binary choice as to whether the prompt heading into the model is safe or not. Kasimir Schulz, a lead security researcher at HiddenLayer, has been researching how to trick these models. Their solution, a technique called "Echogram" involves words with such positive statistical sentiment — such overwhelming good vibes — that it flips that verdict. Learn more about your ad choices. Visit podcastchoices.com/adchoices
What this episode covers
A lot of modern AI models have a kind of security guard layer that sits in front of them. Its job? A binary choice as to whether the prompt heading into the model is safe or not. Kasimir Schulz, a lead security researcher at HiddenLayer, has been researching how to trick these models. Their solution, a technique called "Echogram" involves words with such positive statistical sentiment — such overwhelming good vibes — that it flips that verdict. Learn more about your ad choices. Visit podcastchoices.com/adchoices
NOW PLAYING
=Coffee
No transcript for this episode yet
Similar Episodes
Jul 2, 2026 ·55m
Jun 28, 2026 ·41m
Jun 21, 2026 ·30m
Jun 14, 2026 ·21m